© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 72022
    Prev
    Next
    INDEX
    Explanations

    75 mg/g/ml

    np_acts-logits-general · gemini-2.5-flash-lite

    quantities and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    protect
    0.46
    stores
    0.46
    t
    0.45
    ながら
    0.44
    <0x0D>
    0.44
    stev
    0.43
    s
    0.43
    淨
    0.43
     땅
    0.42
    suz
    0.41
    POSITIVE LOGITS
     exploit
    0.58
     explot
    0.55
     Prony
    0.51
     endured
    0.50
     indentation
    0.50
     abrasion
    0.49
     unbearable
    0.49
     EC
    0.49
     piqu
    0.49
     incessant
    0.48
    Activations Density 0.059%

    No Known Activations